Gecko [ dallasfobana2023.variationbd.com ]

Name	Size	Permission
alphaindex.h	26.54 KB	-rw-r--r--
appendable.h	8.54 KB	-rw-r--r--
basictz.h	9.99 KB	-rw-r--r--
brkiter.h	27.83 KB	-rw-r--r--
bytestream.h	10.75 KB	-rw-r--r--
bytestrie.h	20.8 KB	-rw-r--r--
bytestriebuilder.h	7.48 KB	-rw-r--r--
calendar.h	107.68 KB	-rw-r--r--
caniter.h	7.53 KB	-rw-r--r--
casemap.h	25.42 KB	-rw-r--r--
char16ptr.h	7.22 KB	-rw-r--r--
chariter.h	23.79 KB	-rw-r--r--
choicfmt.h	23.99 KB	-rw-r--r--
coleitr.h	13.77 KB	-rw-r--r--
coll.h	56.28 KB	-rw-r--r--
compactdecimalformat.h	6.88 KB	-rw-r--r--
curramt.h	3.67 KB	-rw-r--r--
currpinf.h	7.3 KB	-rw-r--r--
currunit.h	4.02 KB	-rw-r--r--
datefmt.h	40.7 KB	-rw-r--r--
dbbi.h	1.19 KB	-rw-r--r--
dcfmtsym.h	20.93 KB	-rw-r--r--
decimfmt.h	87.46 KB	-rw-r--r--
displayoptions.h	7.08 KB	-rw-r--r--
docmain.h	7.46 KB	-rw-r--r--
dtfmtsym.h	38.21 KB	-rw-r--r--
dtintrv.h	3.84 KB	-rw-r--r--
dtitvfmt.h	48.87 KB	-rw-r--r--
dtitvinf.h	18.63 KB	-rw-r--r--
dtptngen.h	28.05 KB	-rw-r--r--
dtrule.h	8.66 KB	-rw-r--r--
edits.h	20.73 KB	-rw-r--r--
enumset.h	2.08 KB	-rw-r--r--
errorcode.h	4.84 KB	-rw-r--r--
fieldpos.h	8.69 KB	-rw-r--r--
filteredbrk.h	5.37 KB	-rw-r--r--
fmtable.h	24.36 KB	-rw-r--r--
format.h	12.5 KB	-rw-r--r--
formattednumber.h	6.28 KB	-rw-r--r--
formattedvalue.h	9.75 KB	-rw-r--r--
fpositer.h	3.03 KB	-rw-r--r--
gender.h	3.35 KB	-rw-r--r--
gregocal.h	30.3 KB	-rw-r--r--
icudataver.h	1.02 KB	-rw-r--r--
icuplug.h	12.1 KB	-rw-r--r--
idna.h	12.71 KB	-rw-r--r--
listformatter.h	8.59 KB	-rw-r--r--
localebuilder.h	11.08 KB	-rw-r--r--
localematcher.h	26.86 KB	-rw-r--r--
localpointer.h	19.55 KB	-rw-r--r--
locdspnm.h	7.12 KB	-rw-r--r--
locid.h	48.31 KB	-rw-r--r--
measfmt.h	11.41 KB	-rw-r--r--
measunit.h	108.23 KB	-rw-r--r--
measure.h	4.68 KB	-rw-r--r--
messageformat2.h	18.13 KB	-rw-r--r--
messageformat2_arguments.h	4.3 KB	-rw-r--r--
messageformat2_data_model.h	123 KB	-rw-r--r--
messageformat2_data_model_name...	784 B	-rw-r--r--
messageformat2_formattable.h	38.29 KB	-rw-r--r--
messageformat2_function_regist...	18 KB	-rw-r--r--
messagepattern.h	33.72 KB	-rw-r--r--
msgfmt.h	44.2 KB	-rw-r--r--
normalizer2.h	34.73 KB	-rw-r--r--
normlzr.h	30.79 KB	-rw-r--r--
nounit.h	2.24 KB	-rw-r--r--
numberformatter.h	90.74 KB	-rw-r--r--
numberrangeformatter.h	26.05 KB	-rw-r--r--
numfmt.h	50.16 KB	-rw-r--r--
numsys.h	7.22 KB	-rw-r--r--
parseerr.h	3.08 KB	-rw-r--r--
parsepos.h	5.56 KB	-rw-r--r--
platform.h	26.66 KB	-rw-r--r--
plurfmt.h	25.07 KB	-rw-r--r--
plurrule.h	20.63 KB	-rw-r--r--
ptypes.h	2.16 KB	-rw-r--r--
putil.h	6.32 KB	-rw-r--r--
rbbi.h	32.04 KB	-rw-r--r--
rbnf.h	50.53 KB	-rw-r--r--
rbtz.h	15.75 KB	-rw-r--r--
regex.h	84.45 KB	-rw-r--r--
region.h	9.2 KB	-rw-r--r--
reldatefmt.h	22.36 KB	-rw-r--r--
rep.h	9.38 KB	-rw-r--r--
resbund.h	18.03 KB	-rw-r--r--
schriter.h	6.09 KB	-rw-r--r--
scientificnumberformatter.h	6.44 KB	-rw-r--r--
search.h	22.21 KB	-rw-r--r--
selfmt.h	14.35 KB	-rw-r--r--
simpleformatter.h	12.58 KB	-rw-r--r--
simplenumberformatter.h	9.18 KB	-rw-r--r--
simpletz.h	45.62 KB	-rw-r--r--
smpdtfmt.h	57.06 KB	-rw-r--r--
sortkey.h	11.12 KB	-rw-r--r--
std_string.h	1.05 KB	-rw-r--r--
strenum.h	9.96 KB	-rw-r--r--
stringoptions.h	5.79 KB	-rw-r--r--
stringpiece.h	10.02 KB	-rw-r--r--
stringtriebuilder.h	15.5 KB	-rw-r--r--
stsearch.h	21.43 KB	-rw-r--r--
symtable.h	4.28 KB	-rw-r--r--
tblcoll.h	36.93 KB	-rw-r--r--
timezone.h	45.64 KB	-rw-r--r--
tmunit.h	3.4 KB	-rw-r--r--
tmutamt.h	4.9 KB	-rw-r--r--
tmutfmt.h	7.42 KB	-rw-r--r--
translit.h	65.8 KB	-rw-r--r--
tzfmt.h	42.95 KB	-rw-r--r--
tznames.h	16.85 KB	-rw-r--r--
tzrule.h	34.81 KB	-rw-r--r--
tztrans.h	6.11 KB	-rw-r--r--
ubidi.h	89.61 KB	-rw-r--r--
ubiditransform.h	12.71 KB	-rw-r--r--
ubrk.h	24.43 KB	-rw-r--r--
ucal.h	64.01 KB	-rw-r--r--
ucasemap.h	15.21 KB	-rw-r--r--
ucat.h	5.35 KB	-rw-r--r--
uchar.h	150.13 KB	-rw-r--r--
ucharstrie.h	22.56 KB	-rw-r--r--
ucharstriebuilder.h	7.48 KB	-rw-r--r--
uchriter.h	13.24 KB	-rw-r--r--
uclean.h	11.21 KB	-rw-r--r--
ucnv.h	83.34 KB	-rw-r--r--
ucnv_cb.h	6.58 KB	-rw-r--r--
ucnv_err.h	20.98 KB	-rw-r--r--
ucnvsel.h	6.24 KB	-rw-r--r--
ucol.h	62.7 KB	-rw-r--r--
ucoleitr.h	9.82 KB	-rw-r--r--
uconfig.h	12.56 KB	-rw-r--r--
ucpmap.h	5.54 KB	-rw-r--r--
ucptrie.h	22.51 KB	-rw-r--r--
ucsdet.h	14.69 KB	-rw-r--r--
ucurr.h	16.72 KB	-rw-r--r--
udat.h	62.36 KB	-rw-r--r--
udata.h	15.63 KB	-rw-r--r--
udateintervalformat.h	11.93 KB	-rw-r--r--
udatpg.h	30.13 KB	-rw-r--r--
udisplaycontext.h	5.94 KB	-rw-r--r--
udisplayoptions.h	8.86 KB	-rw-r--r--
uenum.h	7.79 KB	-rw-r--r--
ufieldpositer.h	4.41 KB	-rw-r--r--
uformattable.h	10.97 KB	-rw-r--r--
uformattednumber.h	8.09 KB	-rw-r--r--
uformattedvalue.h	12.25 KB	-rw-r--r--
ugender.h	2.06 KB	-rw-r--r--
uidna.h	33.43 KB	-rw-r--r--
uiter.h	22.75 KB	-rw-r--r--
uldnames.h	10.48 KB	-rw-r--r--
ulistformatter.h	10.78 KB	-rw-r--r--
uloc.h	55.38 KB	-rw-r--r--
ulocale.h	6.35 KB	-rw-r--r--
ulocbuilder.h	16.73 KB	-rw-r--r--
ulocdata.h	11.3 KB	-rw-r--r--
umachine.h	14.59 KB	-rw-r--r--
umisc.h	1.34 KB	-rw-r--r--
umsg.h	24.25 KB	-rw-r--r--
umutablecptrie.h	8.3 KB	-rw-r--r--
unifilt.h	4 KB	-rw-r--r--
unifunct.h	4.05 KB	-rw-r--r--
unimatch.h	6.1 KB	-rw-r--r--
unirepl.h	3.38 KB	-rw-r--r--
uniset.h	66.82 KB	-rw-r--r--
unistr.h	171.33 KB	-rw-r--r--
unorm.h	20.55 KB	-rw-r--r--
unorm2.h	25.71 KB	-rw-r--r--
unum.h	55.16 KB	-rw-r--r--
unumberformatter.h	19.68 KB	-rw-r--r--
unumberoptions.h	5.23 KB	-rw-r--r--
unumberrangeformatter.h	15.35 KB	-rw-r--r--
unumsys.h	7.26 KB	-rw-r--r--
uobject.h	10.66 KB	-rw-r--r--
upluralrules.h	8.79 KB	-rw-r--r--
uregex.h	71.99 KB	-rw-r--r--
uregion.h	9.81 KB	-rw-r--r--
ureldatefmt.h	16.98 KB	-rw-r--r--
urename.h	141.31 KB	-rw-r--r--
urep.h	5.38 KB	-rw-r--r--
ures.h	36.65 KB	-rw-r--r--
uscript.h	27.89 KB	-rw-r--r--
usearch.h	39.21 KB	-rw-r--r--
uset.h	45.56 KB	-rw-r--r--
usetiter.h	9.63 KB	-rw-r--r--
ushape.h	18 KB	-rw-r--r--
usimplenumberformatter.h	7.63 KB	-rw-r--r--
uspoof.h	80.32 KB	-rw-r--r--
usprep.h	8.19 KB	-rw-r--r--
ustdio.h	38.56 KB	-rw-r--r--
ustream.h	1.89 KB	-rw-r--r--
ustring.h	72.13 KB	-rw-r--r--
ustringtrie.h	3.15 KB	-rw-r--r--
utext.h	58.1 KB	-rw-r--r--
utf.h	7.87 KB	-rw-r--r--
utf16.h	23.35 KB	-rw-r--r--
utf32.h	763 B	-rw-r--r--
utf8.h	30.83 KB	-rw-r--r--
utf_old.h	45.8 KB	-rw-r--r--
utmscale.h	13.78 KB	-rw-r--r--
utrace.h	17.18 KB	-rw-r--r--
utrans.h	25.54 KB	-rw-r--r--
utypes.h	33.71 KB	-rw-r--r--
uvernum.h	6.33 KB	-rw-r--r--
uversion.h	5.99 KB	-rw-r--r--
vtzone.h	20.68 KB	-rw-r--r--

Code Editor : uset.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 2002-2014, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  uset.h
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2002mar07
*   created by: Markus W. Scherer
*
*   C version of UnicodeSet.
*/

/**
 * \file
 * \brief C API: Unicode Set
 *
 * This is a C wrapper around the C++ UnicodeSet class.
 */

#ifndef __USET_H__
#define __USET_H__

#include "unicode/utypes.h"
#include "unicode/uchar.h"

#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif   // U_SHOW_CPLUSPLUS_API

#ifndef USET_DEFINED

#ifndef U_IN_DOXYGEN
#define USET_DEFINED
#endif
/**
 * USet is the C API type corresponding to C++ class UnicodeSet.
 * Use the uset_* API to manipulate.  Create with
 * uset_open*, and destroy with uset_close.
 * @stable ICU 2.4
 */
typedef struct USet USet;
#endif

/**
 * Bitmask values to be passed to uset_openPatternOptions() or
 * uset_applyPattern() taking an option parameter.
 *
 * Use at most one of USET_CASE_INSENSITIVE, USET_ADD_CASE_MAPPINGS, USET_SIMPLE_CASE_INSENSITIVE.
 * These case options are mutually exclusive.
 *
 * Undefined options bits are ignored, and reserved for future use.
 *
 * @stable ICU 2.4
 */
enum {
    /**
     * Ignore white space within patterns unless quoted or escaped.
     * @stable ICU 2.4
     */
    USET_IGNORE_SPACE = 1,

/**
     * Enable case insensitive matching.  E.g., "[ab]" with this flag
     * will match 'a', 'A', 'b', and 'B'.  "[^ab]" with this flag will
     * match all except 'a', 'A', 'b', and 'B'. This performs a full
     * closure over case mappings, e.g. 'ſ' (U+017F long s) for 's'.
     *
     * The resulting set is a superset of the input for the code points but
     * not for the strings.
     * It performs a case mapping closure of the code points and adds
     * full case folding strings for the code points, and reduces strings of
     * the original set to their full case folding equivalents.
     *
     * This is designed for case-insensitive matches, for example
     * in regular expressions. The full code point case closure allows checking of
     * an input character directly against the closure set.
     * Strings are matched by comparing the case-folded form from the closure
     * set with an incremental case folding of the string in question.
     *
     * The closure set will also contain single code points if the original
     * set contained case-equivalent strings (like U+00DF for "ss" or "Ss" etc.).
     * This is not necessary (that is, redundant) for the above matching method
     * but results in the same closure sets regardless of whether the original
     * set contained the code point or a string.
     *
     * @stable ICU 2.4
     */
    USET_CASE_INSENSITIVE = 2,

/**
     * Adds all case mappings for each element in the set.
     * This adds the full lower-, title-, and uppercase mappings as well as the full case folding
     * of each existing element in the set.
     *
     * Unlike the “case insensitive” options, this does not perform a closure.
     * For example, it does not add 'ſ' (U+017F long s) for 's',
     * 'K' (U+212A Kelvin sign) for 'k', or replace set strings by their case-folded versions.
     *
     * @stable ICU 3.2
     */
    USET_ADD_CASE_MAPPINGS = 4,

/**
     * Enable case insensitive matching.
     * Same as USET_CASE_INSENSITIVE but using only Simple_Case_Folding (scf) mappings,
     * which map each code point to one code point,
     * not full Case_Folding (cf) mappings, which map some code points to multiple code points.
     *
     * This is designed for case-insensitive matches, for example in certain
     * regular expression implementations where only Simple_Case_Folding mappings are used,
     * such as in ECMAScript (JavaScript) regular expressions.
     *
     * @stable ICU 73
     */
    USET_SIMPLE_CASE_INSENSITIVE = 6
};

/**
 * Argument values for whether span() and similar functions continue while
 * the current character is contained vs. not contained in the set.
 *
 * The functionality is straightforward for sets with only single code points,
 * without strings (which is the common case):
 * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE work the same.
 * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE are inverses of USET_SPAN_NOT_CONTAINED.
 * - span() and spanBack() partition any string the same way when
 * alternating between span(USET_SPAN_NOT_CONTAINED) and
 * span(either "contained" condition).
 * - Using a complemented (inverted) set and the opposite span conditions
 * yields the same results.
 *
 * When a set contains multi-code point strings, then these statements may not
 * be true, depending on the strings in the set (for example, whether they
 * overlap with each other) and the string that is processed.
 * For a set with strings:
 * - The complement of the set contains the opposite set of code points,
 * but the same set of strings.
 * Therefore, complementing both the set and the span conditions
 * may yield different results.
 * - When starting spans at different positions in a string
 * (span(s, ...) vs. span(s+1, ...)) the ends of the spans may be different
 * because a set string may start before the later position.
 * - span(USET_SPAN_SIMPLE) may be shorter than
 * span(USET_SPAN_CONTAINED) because it will not recursively try
 * all possible paths.
 * For example, with a set which contains the three strings "xy", "xya" and "ax",
 * span("xyax", USET_SPAN_CONTAINED) will return 4 but
 * span("xyax", USET_SPAN_SIMPLE) will return 3.
 * span(USET_SPAN_SIMPLE) will never be longer than
 * span(USET_SPAN_CONTAINED).
 * - With either "contained" condition, span() and spanBack() may partition
 * a string in different ways.
 * For example, with a set which contains the two strings "ab" and "ba",
 * and when processing the string "aba",
 * span() will yield contained/not-contained boundaries of { 0, 2, 3 }
 * while spanBack() will yield boundaries of { 0, 1, 3 }.
 *
 * Note: If it is important to get the same boundaries whether iterating forward
 * or backward through a string, then either only span() should be used and
 * the boundaries cached for backward operation, or an ICU BreakIterator
 * could be used.
 *
 * Note: Unpaired surrogates are treated like surrogate code points.
 * Similarly, set strings match only on code point boundaries,
 * never in the middle of a surrogate pair.
 * Illegal UTF-8 sequences are treated like U+FFFD.
 * When processing UTF-8 strings, malformed set strings
 * (strings with unpaired surrogates which cannot be converted to UTF-8)
 * are ignored.
 *
 * @stable ICU 3.8
 */
typedef enum USetSpanCondition {
 /**
 * Continues a span() while there is no set element at the current position.
 * Increments by one code point at a time.
 * Stops before the first set element (character or string).
 * (For code points only, this is like while contains(current)==false).
 *
 * When span() returns, the substring between where it started and the position
 * it returned consists only of characters that are not in the set,
 * and none of its strings overlap with the span.
 *
 * @stable ICU 3.8
 */
 USET_SPAN_NOT_CONTAINED = 0,
 /**
 * Spans the longest substring that is a concatenation of set elements (characters or strings).
 * (For characters only, this is like while contains(current)==true).
 *
 * When span() returns, the substring between where it started and the position
 * it returned consists only of set elements (characters or strings) that are in the set.
 *
 * If a set contains strings, then the span will be the longest substring for which there
 * exists at least one non-overlapping concatenation of set elements (characters or strings).
 * This is equivalent to a POSIX regular expression for <code>(OR of each set element)*</code>.
 * (Java/ICU/Perl regex stops at the first match of an OR.)
 *
 * @stable ICU 3.8
 */
 USET_SPAN_CONTAINED = 1,
 /**
 * Continues a span() while there is a set element at the current position.
 * Increments by the longest matching element at each position.
 * (For characters only, this is like while contains(current)==true).
 *
 * When span() returns, the substring between where it started and the position
 * it returned consists only of set elements (characters or strings) that are in the set.
 *
 * If a set only contains single characters, then this is the same
 * as USET_SPAN_CONTAINED.
 *
 * If a set contains strings, then the span will be the longest substring
 * with a match at each position with the longest single set element (character or string).
 *
 * Use this span condition together with other longest-match algorithms,
 * such as ICU converters (ucnv_getUnicodeSet()).
 *
 * @stable ICU 3.8
 */
 USET_SPAN_SIMPLE = 2,
#ifndef U_HIDE_DEPRECATED_API
 /**
 * One more than the last span condition.
 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 */
 USET_SPAN_CONDITION_COUNT
#endif // U_HIDE_DEPRECATED_API
} USetSpanCondition;

enum {
    /**
     * Capacity of USerializedSet::staticArray.
     * Enough for any single-code point set.
     * Also provides padding for nice sizeof(USerializedSet).
     * @stable ICU 2.4
     */
    USET_SERIALIZED_STATIC_ARRAY_CAPACITY=8
};

/**
 * A serialized form of a Unicode set.  Limited manipulations are
 * possible directly on a serialized set.  See below.
 * @stable ICU 2.4
 */
typedef struct USerializedSet {
    /**
     * The serialized Unicode Set.
     * @stable ICU 2.4
     */
    const uint16_t *array;
    /**
     * The length of the array that contains BMP characters.
     * @stable ICU 2.4
     */
    int32_t bmpLength;
    /**
     * The total length of the array.
     * @stable ICU 2.4
     */
    int32_t length;
    /**
     * A small buffer for the array to reduce memory allocations.
     * @stable ICU 2.4
     */
    uint16_t staticArray[USET_SERIALIZED_STATIC_ARRAY_CAPACITY];
} USerializedSet;

/*********************************************************************
 * USet API
 *********************************************************************/

/**
 * Create an empty USet object.
 * Equivalent to uset_open(1, 0).
 * @return a newly created USet.  The caller must call uset_close() on
 * it when done.
 * @stable ICU 4.2
 */
U_CAPI USet* U_EXPORT2
uset_openEmpty(void);

/**
 * Creates a USet object that contains the range of characters
 * start..end, inclusive. If <code>start > end</code> 
 * then an empty set is created (same as using uset_openEmpty()).
 * @param start first character of the range, inclusive
 * @param end last character of the range, inclusive
 * @return a newly created USet. The caller must call uset_close() on
 * it when done.
 * @stable ICU 2.4
 */
U_CAPI USet* U_EXPORT2
uset_open(UChar32 start, UChar32 end);

/**
 * Creates a set from the given pattern.  See the UnicodeSet class
 * description for the syntax of the pattern language.
 * @param pattern a string specifying what characters are in the set
 * @param patternLength the length of the pattern, or -1 if null
 * terminated
 * @param options bitmask for options to apply to the pattern.
 * Valid options are USET_IGNORE_SPACE and
 * at most one of USET_CASE_INSENSITIVE, USET_ADD_CASE_MAPPINGS, USET_SIMPLE_CASE_INSENSITIVE.
 * These case options are mutually exclusive.
 * @param ec the error code
 * @stable ICU 2.4
 */
U_CAPI USet* U_EXPORT2
uset_openPatternOptions(const UChar* pattern, int32_t patternLength,
                 uint32_t options,
                 UErrorCode* ec);

/**
 * Disposes of the storage used by a USet object.  This function should
 * be called exactly once for objects returned by uset_open().
 * @param set the object to dispose of
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_close(USet* set);

#if U_SHOW_CPLUSPLUS_API

U_NAMESPACE_BEGIN

/**
 * \class LocalUSetPointer
 * "Smart pointer" class, closes a USet via uset_close().
 * For most methods see the LocalPointerBase base class.
 *
 * @see LocalPointerBase
 * @see LocalPointer
 * @stable ICU 4.4
 */
U_DEFINE_LOCAL_OPEN_POINTER(LocalUSetPointer, USet, uset_close);

U_NAMESPACE_END

#endif

/**
 * Returns a copy of this object.
 * If this set is frozen, then the clone will be frozen as well.
 * Use uset_cloneAsThawed() for a mutable clone of a frozen set.
 * @param set the original set
 * @return the newly allocated copy of the set
 * @see uset_cloneAsThawed
 * @stable ICU 3.8
 */
U_CAPI USet * U_EXPORT2
uset_clone(const USet *set);

/**
 * Determines whether the set has been frozen (made immutable) or not.
 * See the ICU4J Freezable interface for details.
 * @param set the set
 * @return true/false for whether the set has been frozen
 * @see uset_freeze
 * @see uset_cloneAsThawed
 * @stable ICU 3.8
 */
U_CAPI UBool U_EXPORT2
uset_isFrozen(const USet *set);

/**
 * Freeze the set (make it immutable).
 * Once frozen, it cannot be unfrozen and is therefore thread-safe
 * until it is deleted.
 * See the ICU4J Freezable interface for details.
 * Freezing the set may also make some operations faster, for example
 * uset_contains() and uset_span().
 * A frozen set will not be modified. (It remains frozen.)
 * @param set the set
 * @return the same set, now frozen
 * @see uset_isFrozen
 * @see uset_cloneAsThawed
 * @stable ICU 3.8
 */
U_CAPI void U_EXPORT2
uset_freeze(USet *set);

/**
 * Clone the set and make the clone mutable.
 * See the ICU4J Freezable interface for details.
 * @param set the set
 * @return the mutable clone
 * @see uset_freeze
 * @see uset_isFrozen
 * @see uset_clone
 * @stable ICU 3.8
 */
U_CAPI USet * U_EXPORT2
uset_cloneAsThawed(const USet *set);

/**
 * Causes the USet object to represent the range <code>start - end</code>.
 * If <code>start > end</code> then this USet is set to an empty range.
 * A frozen set will not be modified.
 * @param set the object to set to the given range
 * @param start first character in the set, inclusive
 * @param end last character in the set, inclusive
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_set(USet* set,
 UChar32 start, UChar32 end);

/**
 * Modifies the set to represent the set specified by the given
 * pattern. See the UnicodeSet class description for the syntax of 
 * the pattern language. See also the User Guide chapter about UnicodeSet.
 * Empties the set passed before applying the pattern.
 * A frozen set will not be modified.
 * @param set The set to which the pattern is to be applied. 
 * @param pattern A pointer to UChar string specifying what characters are in the set.
 * The character at pattern[0] must be a '['.
 * @param patternLength The length of the UChar string. -1 if NUL terminated.
 * @param options A bitmask for options to apply to the pattern.
 * Valid options are USET_IGNORE_SPACE and
 * at most one of USET_CASE_INSENSITIVE, USET_ADD_CASE_MAPPINGS,
 * USET_SIMPLE_CASE_INSENSITIVE.
 * These case options are mutually exclusive.
 * @param status Returns an error if the pattern cannot be parsed.
 * @return Upon successful parse, the value is either
 * the index of the character after the closing ']' 
 * of the parsed pattern.
 * If the status code indicates failure, then the return value 
 * is the index of the error in the source.
 *
 * @stable ICU 2.8
 */
U_CAPI int32_t U_EXPORT2 
uset_applyPattern(USet *set,
 const UChar *pattern, int32_t patternLength,
 uint32_t options,
 UErrorCode *status);

/**
 * Modifies the set to contain those code points which have the given value
 * for the given binary or enumerated property, as returned by
 * u_getIntPropertyValue.  Prior contents of this set are lost.
 * A frozen set will not be modified.
 *
 * @param set the object to contain the code points defined by the property
 *
 * @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1
 * or UCHAR_INT_START..UCHAR_INT_LIMIT-1
 * or UCHAR_MASK_START..UCHAR_MASK_LIMIT-1.
 *
 * @param value a value in the range u_getIntPropertyMinValue(prop)..
 * u_getIntPropertyMaxValue(prop), with one exception.  If prop is
 * UCHAR_GENERAL_CATEGORY_MASK, then value should not be a UCharCategory, but
 * rather a mask value produced by U_GET_GC_MASK().  This allows grouped
 * categories such as [:L:] to be represented.
 *
 * @param ec error code input/output parameter
 *
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_applyIntPropertyValue(USet* set,
                           UProperty prop, int32_t value, UErrorCode* ec);

/**
 * Modifies the set to contain those code points which have the
 * given value for the given property.  Prior contents of this
 * set are lost.
 * A frozen set will not be modified.
 *
 * @param set the object to contain the code points defined by the given
 * property and value alias
 *
 * @param prop a string specifying a property alias, either short or long.
 * The name is matched loosely.  See PropertyAliases.txt for names and a
 * description of loose matching.  If the value string is empty, then this
 * string is interpreted as either a General_Category value alias, a Script
 * value alias, a binary property alias, or a special ID.  Special IDs are
 * matched loosely and correspond to the following sets:
 *
 * "ANY" = [\\u0000-\\U0010FFFF],
 * "ASCII" = [\\u0000-\\u007F],
 * "Assigned" = [:^Cn:].
 *
 * @param propLength the length of the prop, or -1 if NULL
 *
 * @param value a string specifying a value alias, either short or long.
 * The name is matched loosely.  See PropertyValueAliases.txt for names
 * and a description of loose matching.  In addition to aliases listed,
 * numeric values and canonical combining classes may be expressed
 * numerically, e.g., ("nv", "0.5") or ("ccc", "220").  The value string
 * may also be empty.
 *
 * @param valueLength the length of the value, or -1 if NULL
 *
 * @param ec error code input/output parameter
 *
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_applyPropertyAlias(USet* set,
                        const UChar *prop, int32_t propLength,
                        const UChar *value, int32_t valueLength,
                        UErrorCode* ec);

/**
 * Return true if the given position, in the given pattern, appears
 * to be the start of a UnicodeSet pattern.
 *
 * @param pattern a string specifying the pattern
 * @param patternLength the length of the pattern, or -1 if NULL
 * @param pos the given position
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_resemblesPattern(const UChar *pattern, int32_t patternLength,
                      int32_t pos);

/**
 * Returns a string representation of this set.  If the result of
 * calling this function is passed to a uset_openPattern(), it
 * will produce another set that is equal to this one.
 * @param set the set
 * @param result the string to receive the rules, may be NULL
 * @param resultCapacity the capacity of result, may be 0 if result is NULL
 * @param escapeUnprintable if true then convert unprintable
 * character to their hex escape representations, \\uxxxx or
 * \\Uxxxxxxxx.  Unprintable characters are those other than
 * U+000A, U+0020..U+007E.
 * @param ec error code.
 * @return length of string, possibly larger than resultCapacity
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_toPattern(const USet* set,
               UChar* result, int32_t resultCapacity,
               UBool escapeUnprintable,
               UErrorCode* ec);

/**
 * Adds the given character to the given USet.  After this call,
 * uset_contains(set, c) will return true.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param c the character to add
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_add(USet* set, UChar32 c);

/**
 * Adds all of the elements in the specified set to this set if
 * they're not already present. This operation effectively
 * modifies this set so that its value is the union of the two
 * sets. The behavior of this operation is unspecified if the specified
 * collection is modified while the operation is in progress.
 * A frozen set will not be modified.
 *
 * @param set the object to which to add the set
 * @param additionalSet the source set whose elements are to be added to this set.
 * @stable ICU 2.6
 */
U_CAPI void U_EXPORT2
uset_addAll(USet* set, const USet *additionalSet);

/**
 * Adds the given range of characters to the given USet.  After this call,
 * uset_contains(set, start, end) will return true.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param start the first character of the range to add, inclusive
 * @param end the last character of the range to add, inclusive
 * @stable ICU 2.2
 */
U_CAPI void U_EXPORT2
uset_addRange(USet* set, UChar32 start, UChar32 end);

/**
 * Adds the given string to the given USet.  After this call,
 * uset_containsString(set, str, strLen) will return true.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param str the string to add
 * @param strLen the length of the string or -1 if null terminated.
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_addString(USet* set, const UChar* str, int32_t strLen);

/**
 * Adds each of the characters in this string to the set. Note: "ch" => {"c", "h"}
 * If this set already contains any particular character, it has no effect on that character.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param str the source string
 * @param strLen the length of the string or -1 if null terminated.
 * @stable ICU 3.4
 */
U_CAPI void U_EXPORT2
uset_addAllCodePoints(USet* set, const UChar *str, int32_t strLen);

/**
 * Removes the given character from the given USet.  After this call,
 * uset_contains(set, c) will return false.
 * A frozen set will not be modified.
 * @param set the object from which to remove the character
 * @param c the character to remove
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_remove(USet* set, UChar32 c);

/**
 * Removes the given range of characters from the given USet.  After this call,
 * uset_contains(set, start, end) will return false.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param start the first character of the range to remove, inclusive
 * @param end the last character of the range to remove, inclusive
 * @stable ICU 2.2
 */
U_CAPI void U_EXPORT2
uset_removeRange(USet* set, UChar32 start, UChar32 end);

/**
 * Removes the given string to the given USet.  After this call,
 * uset_containsString(set, str, strLen) will return false.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param str the string to remove
 * @param strLen the length of the string or -1 if null terminated.
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_removeString(USet* set, const UChar* str, int32_t strLen);

/**
 * Removes EACH of the characters in this string. Note: "ch" == {"c", "h"}
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @stable ICU 69
 */
U_CAPI void U_EXPORT2
uset_removeAllCodePoints(USet *set, const UChar *str, int32_t length);

/**
 * Removes from this set all of its elements that are contained in the
 * specified set. This operation effectively modifies this
 * set so that its value is the asymmetric set difference of
 * the two sets.
 * A frozen set will not be modified.
 * @param set the object from which the elements are to be removed
 * @param removeSet the object that defines which elements will be
 * removed from this set
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_removeAll(USet* set, const USet* removeSet);

/**
 * Retain only the elements in this set that are contained in the
 * specified range. If <code>start > end</code> then an empty range is
 * retained, leaving the set empty. This is equivalent to
 * a boolean logic AND, or a set INTERSECTION.
 * A frozen set will not be modified.
 *
 * @param set the object for which to retain only the specified range
 * @param start first character, inclusive, of range
 * @param end last character, inclusive, of range
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_retain(USet* set, UChar32 start, UChar32 end);

/**
 * Retains only the specified string from this set if it is present.
 * Upon return this set will be empty if it did not contain s, or
 * will only contain s if it did contain s.
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @stable ICU 69
 */
U_CAPI void U_EXPORT2
uset_retainString(USet *set, const UChar *str, int32_t length);

/**
 * Retains EACH of the characters in this string. Note: "ch" == {"c", "h"}
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @stable ICU 69
 */
U_CAPI void U_EXPORT2
uset_retainAllCodePoints(USet *set, const UChar *str, int32_t length);

/**
 * Retains only the elements in this set that are contained in the
 * specified set. In other words, removes from this set all of
 * its elements that are not contained in the specified set. This
 * operation effectively modifies this set so that its value is
 * the intersection of the two sets.
 * A frozen set will not be modified.
 *
 * @param set the object on which to perform the retain
 * @param retain set that defines which elements this set will retain
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_retainAll(USet* set, const USet* retain);

/**
 * Reallocate this objects internal structures to take up the least
 * possible space, without changing this object's value.
 * A frozen set will not be modified.
 *
 * @param set the object on which to perform the compact
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_compact(USet* set);

/**
 * This is equivalent to
 * <code>uset_complementRange(set, 0, 0x10FFFF)</code>.
 *
 * Note: This performs a symmetric difference with all code points
 * and thus retains all multicharacter strings.
 * In order to achieve a “code point complement” (all code points minus this set),
 * the easiest is to <code>uset_complement(set); uset_removeAllStrings(set);</code>.
 *
 * A frozen set will not be modified.
 * @param set the set
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_complement(USet* set);

/**
 * Complements the specified range in this set. Any character in
 * the range will be removed if it is in this set, or will be
 * added if it is not in this set. If <code>start > end</code>
 * then an empty range is complemented, leaving the set unchanged.
 * This is equivalent to a boolean logic XOR.
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param start first character, inclusive, of range
 * @param end last character, inclusive, of range
 * @stable ICU 69
 */
U_CAPI void U_EXPORT2
uset_complementRange(USet *set, UChar32 start, UChar32 end);

/**
 * Complements the specified string in this set.
 * The string will be removed if it is in this set, or will be added if it is not in this set.
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @stable ICU 69
 */
U_CAPI void U_EXPORT2
uset_complementString(USet *set, const UChar *str, int32_t length);

/**
 * Complements EACH of the characters in this string. Note: "ch" == {"c", "h"}
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @stable ICU 69
 */
U_CAPI void U_EXPORT2
uset_complementAllCodePoints(USet *set, const UChar *str, int32_t length);

/**
 * Complements in this set all elements contained in the specified
 * set.  Any character in the other set will be removed if it is
 * in this set, or will be added if it is not in this set.
 * A frozen set will not be modified.
 *
 * @param set the set with which to complement
 * @param complement set that defines which elements will be xor'ed
 * from this set.
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_complementAll(USet* set, const USet* complement);

/**
 * Removes all of the elements from this set.  This set will be
 * empty after this call returns.
 * A frozen set will not be modified.
 * @param set the set
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_clear(USet* set);

/**
 * Close this set over the given attribute.  For the attribute
 * USET_CASE_INSENSITIVE, the result is to modify this set so that:
 *
 * 1. For each character or string 'a' in this set, all strings or
 * characters 'b' such that foldCase(a) == foldCase(b) are added
 * to this set.
 *
 * 2. For each string 'e' in the resulting set, if e !=
 * foldCase(e), 'e' will be removed.
 *
 * Example: [aq\\u00DF{Bc}{bC}{Fi}] => [aAqQ\\u00DF\\uFB01{ss}{bc}{fi}]
 *
 * (Here foldCase(x) refers to the operation u_strFoldCase, and a
 * == b denotes that the contents are the same, not pointer
 * comparison.)
 *
 * A frozen set will not be modified.
 *
 * @param set the set
 *
 * @param attributes bitmask for attributes to close over.
 * Valid options:
 * At most one of USET_CASE_INSENSITIVE, USET_ADD_CASE_MAPPINGS, USET_SIMPLE_CASE_INSENSITIVE.
 * These case options are mutually exclusive.
 * Unrelated options bits are ignored.
 * @stable ICU 4.2
 */
U_CAPI void U_EXPORT2
uset_closeOver(USet* set, int32_t attributes);

/**
 * Remove all strings from this set.
 *
 * @param set the set
 * @stable ICU 4.2
 */
U_CAPI void U_EXPORT2
uset_removeAllStrings(USet* set);

/**
 * Returns true if the given USet contains no characters and no
 * strings.
 * @param set the set
 * @return true if set is empty
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_isEmpty(const USet* set);

/**
 * @param set the set
 * @return true if this set contains multi-character strings or the empty string.
 * @stable ICU 70
 */
U_CAPI UBool U_EXPORT2
uset_hasStrings(const USet *set);

/**
 * Returns true if the given USet contains the given character.
 * This function works faster with a frozen set.
 * @param set the set
 * @param c The codepoint to check for within the set
 * @return true if set contains c
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_contains(const USet* set, UChar32 c);

/**
 * Returns true if the given USet contains all characters c
 * where start <= c && c <= end.
 * @param set the set
 * @param start the first character of the range to test, inclusive
 * @param end the last character of the range to test, inclusive
 * @return true if set contains the range
 * @stable ICU 2.2
 */
U_CAPI UBool U_EXPORT2
uset_containsRange(const USet* set, UChar32 start, UChar32 end);

/**
 * Returns true if the given USet contains the given string.
 * @param set the set
 * @param str the string
 * @param strLen the length of the string or -1 if null terminated.
 * @return true if set contains str
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_containsString(const USet* set, const UChar* str, int32_t strLen);

/**
 * Returns the index of the given character within this set, where
 * the set is ordered by ascending code point. If the character
 * is not in this set, return -1. The inverse of this method is
 * <code>charAt()</code>.
 * @param set the set
 * @param c the character to obtain the index for
 * @return an index from 0..size()-1, or -1
 * @stable ICU 3.2
 */
U_CAPI int32_t U_EXPORT2
uset_indexOf(const USet* set, UChar32 c);

/**
 * Returns the character at the given index within this set, where
 * the set is ordered by ascending code point. If the index is
 * out of range for characters, returns (UChar32)-1.
 * The inverse of this method is <code>indexOf()</code>.
 *
 * For iteration, this is slower than uset_getRangeCount()/uset_getItemCount()
 * with uset_getItem(), because for each call it skips linearly over <code>index</code>
 * characters in the ranges.
 *
 * @param set the set
 * @param charIndex an index from 0..size()-1 to obtain the char for
 * @return the character at the given index, or (UChar32)-1.
 * @stable ICU 3.2
 */
U_CAPI UChar32 U_EXPORT2
uset_charAt(const USet* set, int32_t charIndex);

/**
 * Returns the number of characters and strings contained in this set.
 * The last (uset_getItemCount() - uset_getRangeCount()) items are strings.
 *
 * This is slower than uset_getRangeCount() and uset_getItemCount() because
 * it counts the code points of all ranges.
 *
 * @param set the set
 * @return a non-negative integer counting the characters and strings
 * contained in set
 * @stable ICU 2.4
 * @see uset_getRangeCount
 */
U_CAPI int32_t U_EXPORT2
uset_size(const USet* set);

/**
 * @param set the set
 * @return the number of ranges in this set.
 * @stable ICU 70
 * @see uset_getItemCount
 * @see uset_getItem
 * @see uset_size
 */
U_CAPI int32_t U_EXPORT2
uset_getRangeCount(const USet *set);

/**
 * Returns the number of items in this set.  An item is either a range
 * of characters or a single multicharacter string.
 * @param set the set
 * @return a non-negative integer counting the character ranges
 * and/or strings contained in set
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_getItemCount(const USet* set);

/**
 * Returns an item of this set. An item is either a range of
 * characters or a single multicharacter string (which can be the empty string).
 *
 * If <code>itemIndex</code> is less than uset_getRangeCount(), then this function returns 0,
 * and the range is <code>*start</code>..<code>*end</code>.
 *
 * If <code>itemIndex</code> is at least uset_getRangeCount() and less than uset_getItemCount(), then
 * this function copies the string into <code>str[strCapacity]</code> and
 * returns the length of the string (0 for the empty string).
 *
 * If <code>itemIndex</code> is out of range, then this function returns -1.
 *
 * Note that 0 is returned for each range as well as for the empty string.
 *
 * @param set the set
 * @param itemIndex a non-negative integer in the range 0..uset_getItemCount(set)-1
 * @param start pointer to variable to receive first character in range, inclusive;
 * can be NULL for a string item
 * @param end pointer to variable to receive last character in range, inclusive;
 * can be NULL for a string item
 * @param str buffer to receive the string, may be NULL
 * @param strCapacity capacity of str, or 0 if str is NULL
 * @param ec error code; U_INDEX_OUTOFBOUNDS_ERROR if the itemIndex is out of range
 * @return the length of the string (0 or >= 2), or 0 if the item is a range,
 * or -1 if the itemIndex is out of range
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_getItem(const USet* set, int32_t itemIndex,
 UChar32* start, UChar32* end,
 UChar* str, int32_t strCapacity,
 UErrorCode* ec);

/**
 * Returns true if set1 contains all the characters and strings
 * of set2. It answers the question, 'Is set1 a superset of set2?'
 * @param set1 set to be checked for containment
 * @param set2 set to be checked for containment
 * @return true if the test condition is met
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_containsAll(const USet* set1, const USet* set2);

/**
 * Returns true if this set contains all the characters
 * of the given string. This is does not check containment of grapheme
 * clusters, like uset_containsString.
 * @param set set of characters to be checked for containment
 * @param str string containing codepoints to be checked for containment
 * @param strLen the length of the string or -1 if null terminated.
 * @return true if the test condition is met
 * @stable ICU 3.4
 */
U_CAPI UBool U_EXPORT2
uset_containsAllCodePoints(const USet* set, const UChar *str, int32_t strLen);

/**
 * Returns true if set1 contains none of the characters and strings
 * of set2. It answers the question, 'Is set1 a disjoint set of set2?'
 * @param set1 set to be checked for containment
 * @param set2 set to be checked for containment
 * @return true if the test condition is met
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_containsNone(const USet* set1, const USet* set2);

/**
 * Returns true if set1 contains some of the characters and strings
 * of set2. It answers the question, 'Does set1 and set2 have an intersection?'
 * @param set1 set to be checked for containment
 * @param set2 set to be checked for containment
 * @return true if the test condition is met
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_containsSome(const USet* set1, const USet* set2);

/**
 * Returns the length of the initial substring of the input string which
 * consists only of characters and strings that are contained in this set
 * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
 * or only of characters and strings that are not contained
 * in this set (USET_SPAN_NOT_CONTAINED).
 * See USetSpanCondition for details.
 * Similar to the strspn() C library function.
 * Unpaired surrogates are treated according to contains() of their surrogate code points.
 * This function works faster with a frozen set and with a non-negative string length argument.
 * @param set the set
 * @param s start of the string
 * @param length of the string; can be -1 for NUL-terminated
 * @param spanCondition specifies the containment condition
 * @return the length of the initial substring according to the spanCondition;
 *         0 if the start of the string does not fit the spanCondition
 * @stable ICU 3.8
 * @see USetSpanCondition
 */
U_CAPI int32_t U_EXPORT2
uset_span(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);

/**
 * Returns the start of the trailing substring of the input string which
 * consists only of characters and strings that are contained in this set
 * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
 * or only of characters and strings that are not contained
 * in this set (USET_SPAN_NOT_CONTAINED).
 * See USetSpanCondition for details.
 * Unpaired surrogates are treated according to contains() of their surrogate code points.
 * This function works faster with a frozen set and with a non-negative string length argument.
 * @param set the set
 * @param s start of the string
 * @param length of the string; can be -1 for NUL-terminated
 * @param spanCondition specifies the containment condition
 * @return the start of the trailing substring according to the spanCondition;
 *         the string length if the end of the string does not fit the spanCondition
 * @stable ICU 3.8
 * @see USetSpanCondition
 */
U_CAPI int32_t U_EXPORT2
uset_spanBack(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);

/**
 * Returns the length of the initial substring of the input string which
 * consists only of characters and strings that are contained in this set
 * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
 * or only of characters and strings that are not contained
 * in this set (USET_SPAN_NOT_CONTAINED).
 * See USetSpanCondition for details.
 * Similar to the strspn() C library function.
 * Malformed byte sequences are treated according to contains(0xfffd).
 * This function works faster with a frozen set and with a non-negative string length argument.
 * @param set the set
 * @param s start of the string (UTF-8)
 * @param length of the string; can be -1 for NUL-terminated
 * @param spanCondition specifies the containment condition
 * @return the length of the initial substring according to the spanCondition;
 *         0 if the start of the string does not fit the spanCondition
 * @stable ICU 3.8
 * @see USetSpanCondition
 */
U_CAPI int32_t U_EXPORT2
uset_spanUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);

/**
 * Returns the start of the trailing substring of the input string which
 * consists only of characters and strings that are contained in this set
 * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
 * or only of characters and strings that are not contained
 * in this set (USET_SPAN_NOT_CONTAINED).
 * See USetSpanCondition for details.
 * Malformed byte sequences are treated according to contains(0xfffd).
 * This function works faster with a frozen set and with a non-negative string length argument.
 * @param set the set
 * @param s start of the string (UTF-8)
 * @param length of the string; can be -1 for NUL-terminated
 * @param spanCondition specifies the containment condition
 * @return the start of the trailing substring according to the spanCondition;
 *         the string length if the end of the string does not fit the spanCondition
 * @stable ICU 3.8
 * @see USetSpanCondition
 */
U_CAPI int32_t U_EXPORT2
uset_spanBackUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);

/**
 * Returns true if set1 contains all of the characters and strings
 * of set2, and vis versa. It answers the question, 'Is set1 equal to set2?'
 * @param set1 set to be checked for containment
 * @param set2 set to be checked for containment
 * @return true if the test condition is met
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_equals(const USet* set1, const USet* set2);

/*********************************************************************
 * Serialized set API
 *********************************************************************/

/**
 * Serializes this set into an array of 16-bit integers. Serialization
 * (currently) only records the characters in the set; multicharacter
 * strings are ignored.
 *
 * The array
 * has following format (each line is one 16-bit integer):
 *
 * length = (n+2*m) | (m!=0?0x8000:0)
 * bmpLength = n; present if m!=0
 * bmp[0]
 * bmp[1]
 * ...
 * bmp[n-1]
 * supp-high[0]
 * supp-low[0]
 * supp-high[1]
 * supp-low[1]
 * ...
 * supp-high[m-1]
 * supp-low[m-1]
 *
 * The array starts with a header. After the header are n bmp
 * code points, then m supplementary code points. Either n or m
 * or both may be zero. n+2*m is always <= 0x7FFF.
 *
 * If there are no supplementary characters (if m==0) then the
 * header is one 16-bit integer, 'length', with value n.
 *
 * If there are supplementary characters (if m!=0) then the header
 * is two 16-bit integers. The first, 'length', has value
 * (n+2*m)|0x8000. The second, 'bmpLength', has value n.
 *
 * After the header the code points are stored in ascending order.
 * Supplementary code points are stored as most significant 16
 * bits followed by least significant 16 bits.
 *
 * @param set the set
 * @param dest pointer to buffer of destCapacity 16-bit integers.
 * May be NULL only if destCapacity is zero.
 * @param destCapacity size of dest, or zero. Must not be negative.
 * @param pErrorCode pointer to the error code. Will be set to
 * U_INDEX_OUTOFBOUNDS_ERROR if n+2*m > 0x7FFF. Will be set to
 * U_BUFFER_OVERFLOW_ERROR if n+2*m+(m!=0?2:1) > destCapacity.
 * @return the total length of the serialized format, including
 * the header, that is, n+2*m+(m!=0?2:1), or 0 on error other
 * than U_BUFFER_OVERFLOW_ERROR.
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_serialize(const USet* set, uint16_t* dest, int32_t destCapacity, UErrorCode* pErrorCode);

/**
 * Given a serialized array, fill in the given serialized set object.
 * @param fillSet pointer to result
 * @param src pointer to start of array
 * @param srcLength length of array
 * @return true if the given array is valid, otherwise false
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_getSerializedSet(USerializedSet* fillSet, const uint16_t* src, int32_t srcLength);

/**
 * Set the USerializedSet to contain the given character (and nothing
 * else).
 * @param fillSet pointer to result
 * @param c The codepoint to set
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_setSerializedToOne(USerializedSet* fillSet, UChar32 c);

/**
 * Returns true if the given USerializedSet contains the given
 * character.
 * @param set the serialized set
 * @param c The codepoint to check for within the set
 * @return true if set contains c
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_serializedContains(const USerializedSet* set, UChar32 c);

/**
 * Returns the number of disjoint ranges of characters contained in
 * the given serialized set.  Ignores any strings contained in the
 * set.
 * @param set the serialized set
 * @return a non-negative integer counting the character ranges
 * contained in set
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_getSerializedRangeCount(const USerializedSet* set);

/**
 * Returns a range of characters contained in the given serialized
 * set.
 * @param set the serialized set
 * @param rangeIndex a non-negative integer in the range 0..
 * uset_getSerializedRangeCount(set)-1
 * @param pStart pointer to variable to receive first character
 * in range, inclusive
 * @param pEnd pointer to variable to receive last character in range,
 * inclusive
 * @return true if rangeIndex is valid, otherwise false
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_getSerializedRange(const USerializedSet* set, int32_t rangeIndex,
                        UChar32* pStart, UChar32* pEnd);

#endif

${this.title}

Code Editor : uset.h